Merge branch 'main' into feature/odsc68406/amlx_global_explainer

Author: ahosler

.github/workflows/run-forecast-unit-tests.yml

@@ -56,6 +56,6 @@ jobs:
           $CONDA/bin/conda init
           source /home/runner/.bashrc
           pip install -r test-requirements-operators.txt
-          pip install "oracle-automlx[forecasting]>=24.4.1"
+          pip install "oracle-automlx[forecasting]>=25.1.1"
           pip install pandas>=2.2.0
           python -m pytest -v -p no:warnings --durations=5 tests/operators/forecast

ads/opctl/anomaly_detection.py

@@ -0,0 +1,11 @@
+#!/usr/bin/env python
+
+# Copyright (c) 2025 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+
+from ads.opctl.operator.lowcode.anomaly.__main__ import operate
+from ads.opctl.operator.lowcode.anomaly.operator_config import AnomalyOperatorConfig
+
+if __name__ == "__main__":
+    config = AnomalyOperatorConfig()
+    operate(config)

ads/opctl/forecast.py

@@ -0,0 +1,11 @@
+#!/usr/bin/env python
+
+# Copyright (c) 2025 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+
+from ads.opctl.operator.lowcode.forecast.__main__ import operate
+from ads.opctl.operator.lowcode.forecast.operator_config import ForecastOperatorConfig
+
+if __name__ == "__main__":
+    config = ForecastOperatorConfig()
+    operate(config)

ads/opctl/operator/lowcode/forecast/__main__.py

@@ -1,7 +1,6 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*--
 
-# Copyright (c) 2023, 2024 Oracle and/or its affiliates.
+# Copyright (c) 2023, 2025 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
 import json
@@ -15,17 +14,17 @@
 from ads.opctl.operator.common.const import ENV_OPERATOR_ARGS
 from ads.opctl.operator.common.utils import _parse_input_args
 
+from .model.forecast_datasets import ForecastDatasets, ForecastResults
 from .operator_config import ForecastOperatorConfig
-from .model.forecast_datasets import ForecastDatasets
 from .whatifserve import ModelDeploymentManager
 
 
-def operate(operator_config: ForecastOperatorConfig) -> None:
+def operate(operator_config: ForecastOperatorConfig) -> ForecastResults:
     """Runs the forecasting operator."""
     from .model.factory import ForecastOperatorModelFactory
 
     datasets = ForecastDatasets(operator_config)
-    ForecastOperatorModelFactory.get_model(
+    results = ForecastOperatorModelFactory.get_model(
         operator_config, datasets
     ).generate_report()
     # saving to model catalog
@@ -36,6 +35,7 @@ def operate(operator_config: ForecastOperatorConfig) -> None:
         if spec.what_if_analysis.model_deployment:
             mdm.create_deployment()
         mdm.save_deployment_info()
+    return results
 
 
 def verify(spec: Dict, **kwargs: Dict) -> bool:

ads/opctl/operator/lowcode/forecast/model/automlx.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-# Copyright (c) 2023, 2024 Oracle and/or its affiliates.
+# Copyright (c) 2023, 2025 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 import logging
 import os
@@ -66,8 +66,7 @@ def preprocess(self, data, series_id):  # TODO: re-use self.le for explanations
     @runtime_dependency(
         module="automlx",
         err_msg=(
-            "Please run `pip3 install oracle-automlx>=23.4.1` and "
-            "`pip3 install oracle-automlx[forecasting]>=23.4.1` "
+            "Please run `pip3 install oracle-automlx[forecasting]>=25.1.1` "
             "to install the required dependencies for automlx."
         ),
     )
@@ -105,7 +104,7 @@ def _build_model(self) -> pd.DataFrame:
             engine_opts = (
                 None
                 if engine_type == "local"
-                else ({"ray_setup": {"_temp_dir": "/tmp/ray-temp"}},)
+                else {"ray_setup": {"_temp_dir": "/tmp/ray-temp"}}
             )
             init(
                 engine=engine_type,

ads/opctl/operator/lowcode/forecast/model/base_model.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python
 
-# Copyright (c) 2023, 2024 Oracle and/or its affiliates.
+# Copyright (c) 2023, 2025 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
 import logging
@@ -51,7 +51,7 @@
     SupportedModels,
 )
 from ..operator_config import ForecastOperatorConfig, ForecastOperatorSpec
-from .forecast_datasets import ForecastDatasets
+from .forecast_datasets import ForecastDatasets, ForecastResults
 
 logging.getLogger("report_creator").setLevel(logging.WARNING)
 
@@ -350,11 +350,12 @@ def generate_report(self):
                 )
 
             # save the report and result CSV
-            self._save_report(
+            return self._save_report(
                 report_sections=report_sections,
                 result_df=result_df,
                 metrics_df=self.eval_metrics,
                 test_metrics_df=self.test_eval_metrics,
+                test_data=test_data,
             )
 
     def _test_evaluate_metrics(self, elapsed_time=0):
@@ -471,10 +472,12 @@ def _save_report(
         result_df: pd.DataFrame,
         metrics_df: pd.DataFrame,
         test_metrics_df: pd.DataFrame,
+        test_data: pd.DataFrame,
     ):
         """Saves resulting reports to the given folder."""
 
         unique_output_dir = self.spec.output_directory.url
+        results = ForecastResults()
 
         if ObjectStorageDetails.is_oci_path(unique_output_dir):
             storage_options = default_signer()
@@ -500,6 +503,11 @@ def _save_report(
                         f2.write(f1.read())
 
         # forecast csv report
+        # todo: add test data into forecast.csv
+        # if self.spec.test_data is not None:
+        #     test_data_dict = test_data.get_dict_by_series()
+        #     for series_id, test_data_values in test_data_dict.items():
+        #         result_df[DataColumns.Series] = test_data_values[]
         result_df = (
             result_df
             if self.target_cat_col
@@ -511,6 +519,7 @@ def _save_report(
             format="csv",
             storage_options=storage_options,
         )
+        results.set_forecast(result_df)
 
         # metrics csv report
         if self.spec.generate_metrics:
@@ -520,17 +529,19 @@ def _save_report(
                 else "Series 1"
             )
             if metrics_df is not None:
+                metrics_df_formatted = metrics_df.reset_index().rename(
+                    {"index": "metrics", "Series 1": metrics_col_name}, axis=1
+                )
                 write_data(
-                    data=metrics_df.reset_index().rename(
-                        {"index": "metrics", "Series 1": metrics_col_name}, axis=1
-                    ),
+                    data=metrics_df_formatted,
                     filename=os.path.join(
                         unique_output_dir, self.spec.metrics_filename
                     ),
                     format="csv",
                     storage_options=storage_options,
                     index=False,
                 )
+                results.set_metrics(metrics_df_formatted)
             else:
                 logger.warn(
                     f"Attempted to generate the {self.spec.metrics_filename} file with the training metrics, however the training metrics could not be properly generated."
@@ -539,17 +550,19 @@ def _save_report(
             # test_metrics csv report
             if self.spec.test_data is not None:
                 if test_metrics_df is not None:
+                    test_metrics_df_formatted = test_metrics_df.reset_index().rename(
+                        {"index": "metrics", "Series 1": metrics_col_name}, axis=1
+                    )
                     write_data(
-                        data=test_metrics_df.reset_index().rename(
-                            {"index": "metrics", "Series 1": metrics_col_name}, axis=1
-                        ),
+                        data=test_metrics_df_formatted,
                         filename=os.path.join(
                             unique_output_dir, self.spec.test_metrics_filename
                         ),
                         format="csv",
                         storage_options=storage_options,
                         index=False,
                     )
+                    results.set_test_metrics(test_metrics_df_formatted)
                 else:
                     logger.warn(
                         f"Attempted to generate the {self.spec.test_metrics_filename} file with the test metrics, however the test metrics could not be properly generated."
@@ -567,6 +580,7 @@ def _save_report(
                         storage_options=storage_options,
                         index=True,
                     )
+                    results.set_global_explanations(self.formatted_global_explanation)
                 else:
                     logger.warn(
                         f"Attempted to generate global explanations for the {self.spec.global_explanation_filename} file, but an issue occured in formatting the explanations."
@@ -582,6 +596,7 @@ def _save_report(
                         storage_options=storage_options,
                         index=True,
                     )
+                    results.set_local_explanations(self.formatted_local_explanation)
                 else:
                     logger.warn(
                         f"Attempted to generate local explanations for the {self.spec.local_explanation_filename} file, but an issue occured in formatting the explanations."
@@ -602,10 +617,12 @@ def _save_report(
                 index=True,
                 indent=4,
             )
+            results.set_model_parameters(self.model_parameters)
 
         # model pickle
         if self.spec.generate_model_pickle:
             self._save_model(unique_output_dir, storage_options)
+            results.set_models(self.models)
 
         logger.info(
             f"The outputs have been successfully "
@@ -625,8 +642,10 @@ def _save_report(
                 index=True,
                 indent=4,
             )
+            results.set_errors_dict(self.errors_dict)
         else:
             logger.info("All modeling completed successfully.")
+        return results
 
     def preprocess(self, df, series_id):
         """The method that needs to be implemented on the particular model level."""

ads/opctl/operator/lowcode/forecast/model/forecast_datasets.py

@@ -1,8 +1,10 @@
 #!/usr/bin/env python
 
-# Copyright (c) 2023, 2024 Oracle and/or its affiliates.
+# Copyright (c) 2023, 2025 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
+from typing import Dict, List
+
 import pandas as pd
 
 from ads.opctl import logger
@@ -167,7 +169,7 @@ def get_data_multi_indexed(self):
                 self.historical_data.data,
                 self.additional_data.data,
             ],
-            axis=1
+            axis=1,
         )
 
     def get_data_by_series(self, include_horizon=True):
@@ -416,3 +418,59 @@ def get_forecast_long(self):
         for df in self.series_id_map.values():
             output = pd.concat([output, df])
         return output.reset_index(drop=True)
+
+
+class ForecastResults:
+    """
+    Forecast Results contains all outputs from the forecast run.
+    This class is returned to users who use the Forecast's `operate` method.
+
+    """
+
+    def set_forecast(self, df: pd.DataFrame):
+        self.forecast = df
+
+    def get_forecast(self):
+        return getattr(self, "forecast", None)
+
+    def set_metrics(self, df: pd.DataFrame):
+        self.metrics = df
+
+    def get_metrics(self):
+        return getattr(self, "metrics", None)
+
+    def set_test_metrics(self, df: pd.DataFrame):
+        self.test_metrics = df
+
+    def get_test_metrics(self):
+        return getattr(self, "test_metrics", None)
+
+    def set_local_explanations(self, df: pd.DataFrame):
+        self.local_explanations = df
+
+    def get_local_explanations(self):
+        return getattr(self, "local_explanations", None)
+
+    def set_global_explanations(self, df: pd.DataFrame):
+        self.global_explanations = df
+
+    def get_global_explanations(self):
+        return getattr(self, "global_explanations", None)
+
+    def set_model_parameters(self, df: pd.DataFrame):
+        self.model_parameters = df
+
+    def get_model_parameters(self):
+        return getattr(self, "model_parameters", None)
+
+    def set_models(self, models: List):
+        self.models = models
+
+    def get_models(self):
+        return getattr(self, "models", None)
+
+    def set_errors_dict(self, errors_dict: Dict):
+        self.errors_dict = errors_dict
+
+    def get_errors_dict(self):
+        return getattr(self, "errors_dict", None)